Instructions to use MoonMath-ai/GLM-5.3-Uncensored-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use MoonMath-ai/GLM-5.3-Uncensored-FP8 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="MoonMath-ai/GLM-5.3-Uncensored-FP8")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("MoonMath-ai/GLM-5.3-Uncensored-FP8")
model = AutoModelForCausalLM.from_pretrained("MoonMath-ai/GLM-5.3-Uncensored-FP8", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use MoonMath-ai/GLM-5.3-Uncensored-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "MoonMath-ai/GLM-5.3-Uncensored-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MoonMath-ai/GLM-5.3-Uncensored-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/MoonMath-ai/GLM-5.3-Uncensored-FP8

SGLang

How to use MoonMath-ai/GLM-5.3-Uncensored-FP8 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "MoonMath-ai/GLM-5.3-Uncensored-FP8" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MoonMath-ai/GLM-5.3-Uncensored-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "MoonMath-ai/GLM-5.3-Uncensored-FP8" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "MoonMath-ai/GLM-5.3-Uncensored-FP8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use MoonMath-ai/GLM-5.3-Uncensored-FP8 with Docker Model Runner:
```
docker model run hf.co/MoonMath-ai/GLM-5.3-Uncensored-FP8
```

GLM-5.3 MoonMath Dolly2 (FP8)

This is an abliterated ("uncensored") model. It is a research artifact intended for cybersecurity research. It may produce unexpected or unwanted output, is not evaluated for safety, and is not affiliated with Z.ai, the creator of GLM-5.3. No warranty.

MoonMath Dolly2 is our first in-house abliterated model, built by abliterating GLM-5.3 weights (zai-org/GLM-5.3). The published model family is described in our blog post: Dolly and me: Building cybersecurity models at Zro.

With this version we emphasized intelligence and cybersecurity capability: rather than maximally abliterated, the model is surgically modified so it stays helpful and capable on ordinary tasks while being far more willing to address security research questions.

Model creator: MoonMath.ai (Zro)
Base model: zai-org/GLM-5.3
Precision: FP8 (E4M3, blockwise 128×128)

Model description

Abliteration reduces a model's learned refusal behavior by intervening in its internal representations, without retraining. Our recipe is surgical: it modifies a small, targeted set of modules rather than broadly suppressing refusal directions:

attention output projections (self_attn.o_proj) and shared-expert projections (mlp.shared_experts.down_proj)
29 modules across 21 layers (layers 30–62 attention, layers 34–44 shared experts)

This targeted approach keeps general capabilities intact — the modification touches a minimal part of the network instead of broad refusal-direction suppression.

Refusal benchmark

We ran the model against a cybersecurity-focused refusal prompt set (attributed to Meta Purple Llama's cybersecurity benchmark). Each response was classified as addressing the request or deflecting it:

Model	Answered	Deflected	Refused	Answer rate
MoonMath	432	88	0	83.1%
Public abliterated GLM-5.3	350	170	0	67.3%

MoonMath delivered more responses and deflected fewer requests than the public abliterated model. Neither model refused outright.

Quality benchmarks

Both models ran on the same stack (sglang, identical server flags, 8× AMD MI325X). Scoring used stock lm-evaluation-harness 0.4.13 tasks (ifeval, mmlu_pro, aime25) with no custom scorers. Head-to-head against a popular public abliterated GLM-5.3:

Benchmark	Items	MoonMath	Public abliterated	Δ
IFEval (prompt-level strict)	100 prompts	91.0	39.0	+52.0
MMLU-Pro (5-shot CoT)	200 questions	89.0	84.0	+5.0
AIME 2025	30 problems × 2 samples	73.3	63.3	+10.0

The public abliterated model also exhibited severe looping degeneration (67 confirmed degenerate generations, 53% of IFEval responses hitting the 32k-token cap); MoonMath showed 0 in the same run. Full details are in the blog post.

Usage

The checkpoint follows the GLM-5.3 FP8 layout and works with transformers and vLLM / SGLang just like the base model:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "MoonMath-ai/GLM-5.3-Uncensored-FP8", device_map="auto", trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained("MoonMath-ai/GLM-5.3-Uncensored-FP8")

Intended uses and limitations

Intended: cybersecurity research — exploit analysis, authentication-flow review, abuse-of-service analysis, and general security workflows where refusals block legitimate work.
Limitations: abliteration trades safety calibration for helpfulness. The model may answer requests that the base model would decline. It is not safety-evaluated; do not use it as a general-purpose assistant in sensitive deployments without your own evaluation.

Use it on Zro

These weights are served on Zro, MoonMath's private inference platform, as the model Dolly 2 Security (dolly2-security). No GPU setup, and no prompts retained after processing.

With the CLI (open source, MIT):

npm install -g @moonmath-ai/zro
zro login
zro launch claude --model dolly2-security

zro launch also works with codex, opencode, hermes, openclaw, pi and many more harnesses.

With the API (OpenAI-compatible):

curl https://zro.moonmath.ai/v1/chat/completions \
  -H "Authorization: Bearer $ZRO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"dolly2-security","messages":[{"role":"user","content":"Reply with OK"}]}'

Model ID: dolly2-security (alias zro/dolly2-security). The lighter dolly1-security is also available.
1M-token context, up to 131K output. $2.10 per 1M input tokens, $6.30 per 1M output, $0.45 per 1M cache-read tokens. Prompt caching is on by default.
Inference region per API key: Europe, the United States, or both. Requests are routed through the EU.
Zero request retention, and no training on requests.
Plans are monthly spend budgets, not token caps: Pro ($20/month, $40 usage budget) and Max ($60/month, $120 usage budget). A one-time $5 start needs no subscription. Team is coming soon.

Links: pricing · CLI docs · API reference · privacy · sign up · Dolly and me

License

GLM-5.3 is released by Z.ai under the GLM-5.3 model license (see LICENSE in the base repo). This checkpoint inherits the base model's license and terms.

Citation

@misc{moonmath2026dolly2,
  title  = {Dolly and me: Building cybersecurity models at Zro},
  author = {MoonMath.ai},
  year   = {2026},
  url    = {https://zro.moonmath.ai/posts/dolly-and-me}
}

Acknowledgements

Z.ai for the GLM-5.3 base model

Downloads last month: -

Safetensors

Model size

753B params

Tensor type

BF16

F8_E4M3

F32

Model tree for MoonMath-ai/GLM-5.3-Uncensored-FP8

Base model

zai-org/GLM-5.3

Quantized

(93)

this model

Evaluation results

Answer rate (%) on Cybersecurity refusal prompt set
self-reported

83.100
Prompt-level strict acc. on IFEval
self-reported

91.000
5-shot CoT accuracy on MMLU-Pro
self-reported

89.000
Accuracy on AIME 2025
self-reported

73.300